Files
FabledCurator/backend/app/api/gallery.py
T
bvandeusen ad2a5fc5fe
CI / lint (push) Successful in 3s
CI / frontend-build (push) Successful in 24s
CI / backend-lint-and-test (push) Successful in 39s
CI / integration (push) Successful in 3m48s
feat(system-tags): process vs chrome groups + WIP provisional auto-apply (#1464)
Backend for the system-tag behavior refactor (milestone #157). editor screenshot
moves from chrome (hidden) to the PROCESS group (shown, like wip); wip+editor gain
provisional auto-apply so they stop needing endless manual identification —
without a runaway loop.

- tag.py: split PRESENTATION_SYSTEM_TAGS → CHROME_SYSTEM_TAGS (banner) +
  PROCESS_SYSTEM_TAGS (wip, editor screenshot).
- heads.py: generalize presentation_auto_apply_sweep → system_tag_auto_apply_sweep
  (mode chrome|process). Same Guard 1 (skip human/confirmed) + Guard 2 (ring-loud
  conflict → PresentationReview). process mode uses source 'process_auto' and does
  NOT hide (hide is a gallery-query effect of group membership).
- training_data._AUTO_SOURCES += 'process_auto' → the head never trains on its own
  auto-applied output; only wip_title/manual train it (the runaway break).
- ml_settings: process_auto_apply_enabled (OFF, opt-in) + threshold + conflict
  threshold. presentation_review.mode ('chrome'|'process'). Migration 0086.
- gallery_service: default-hide reads CHROME only (editor now shows); Explore
  neighbors exclude the whole PROCESS group.
- tasks/ml + celery beat: scheduled_process_auto_apply (daily, opt-in); prune
  covers both modes.
- api: ml_admin process_* CRUD+validation; hidden-review returns mode.
- tests: rename chrome sweep calls; new test_process_auto_apply (apply, guards,
  mode flag, no-self-train); gallery test asserts editor now visible.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-12 23:15:59 -04:00

338 lines
13 KiB
Python

"""Gallery API: cursor scroll, timeline, jump, image detail, facets."""
from datetime import UTC, datetime, timedelta
from quart import Blueprint, jsonify, request
from sqlalchemy import delete, select, update
from sqlalchemy.orm import aliased
from ..extensions import get_session
from ..models import (
ImageRecord,
PresentationReview,
Tag,
TagSuggestionRejection,
)
from ..models.tag import image_tag
from ..services.gallery_service import GalleryService, image_url, thumbnail_url
gallery_bp = Blueprint("gallery", __name__, url_prefix="/api/gallery")
def _image_json(i):
"""Serialize a GalleryImage for the scroll/similar list responses."""
return {
"id": i.id,
"sha256": i.sha256,
"mime": i.mime,
"width": i.width,
"height": i.height,
"created_at": i.created_at.isoformat(),
"posted_at": i.posted_at.isoformat() if i.posted_at else None,
"thumbnail_url": i.thumbnail_url,
"artist": i.artist,
}
def _parse_date(raw):
"""Parse a YYYY-MM-DD query value to a UTC midnight datetime, or None.
Raises ValueError (→ 400) on a malformed value."""
if not raw:
return None
return datetime.strptime(raw, "%Y-%m-%d").replace(tzinfo=UTC)
def _parse_filters():
"""Parse the composable gallery filters from query args, returning
``(filters_dict, sort)``. Raises ValueError (→ 400) on malformed ids/dates.
The structured tag filter (#6) is AND-of-OR plus exclusions:
- `tag_id` accepts a single id or a comma-separated list — all ANDed
(the include common case; back-compat).
- `tag_or` is REPEATABLE; each instance is a comma-separated OR-group, and
the image must match at least one tag from EACH group (groups ANDed).
- `tag_not` is a comma-separated exclude list (image must carry none).
`media` is image|video; `sort` is newest|oldest|posted_new|posted_old
(default posted_new); `platform` selects one
platform (or the UNSOURCED_PLATFORM sentinel); `untagged`/`no_artist` are
boolean flags; `date_from`/`date_to` are inclusive calendar-day bounds
(date_to is widened by a day so the whole day is covered by the service's
half-open `< date_to`)."""
tag_raw = request.args.get("tag_id")
tag_ids = (
[int(x) for x in tag_raw.split(",") if x.strip()] if tag_raw else None
) or None
tag_or_groups = [
grp for raw in request.args.getlist("tag_or")
if (grp := [int(x) for x in raw.split(",") if x.strip()])
] or None
not_raw = request.args.get("tag_not")
tag_exclude = (
[int(x) for x in not_raw.split(",") if x.strip()] if not_raw else None
) or None
post_id_raw = request.args.get("post_id")
post_id = int(post_id_raw) if post_id_raw else None
artist_id_raw = request.args.get("artist_id")
artist_id = int(artist_id_raw) if artist_id_raw else None
media = request.args.get("media")
media_type = media if media in ("image", "video") else None
# newest/oldest key off effective_date (primary post / download); posted_new/
# posted_old off earliest_post_date (original publish across all posts). The
# default is posted_new so the grid leads with original publish date, not the
# download/repost the primary post points at (operator-flagged 2026-07-01).
sort = request.args.get("sort")
sort = sort if sort in ("newest", "oldest", "posted_new", "posted_old") else "posted_new"
platform = request.args.get("platform") or None
untagged = request.args.get("untagged") in ("1", "true", "yes")
no_artist = request.args.get("no_artist") in ("1", "true", "yes")
# Show the presentation chrome (banner / editor screenshot) that the default
# gallery hides — the Hidden view sets this (milestone 141).
include_hidden = request.args.get("include_hidden") in ("1", "true", "yes")
date_from = _parse_date(request.args.get("date_from"))
date_to = _parse_date(request.args.get("date_to"))
if date_to is not None:
date_to += timedelta(days=1) # inclusive of the date_to calendar day
filters = {
"tag_ids": tag_ids, "post_id": post_id, "artist_id": artist_id,
"media_type": media_type,
"tag_or_groups": tag_or_groups, "tag_exclude": tag_exclude,
"platform": platform,
"untagged": untagged, "no_artist": no_artist,
"date_from": date_from, "date_to": date_to,
"include_hidden": include_hidden,
}
return filters, sort
@gallery_bp.route("/scroll", methods=["GET"])
async def scroll():
cursor = request.args.get("cursor") or None
try:
limit = int(request.args.get("limit", "50"))
filters, sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter or limit parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
page = await svc.scroll(
cursor=cursor, limit=limit, sort=sort, **filters,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
{
"images": [_image_json(i) for i in page.images],
"next_cursor": page.next_cursor,
"date_groups": [
{"year": y, "month": m, "image_ids": ids} for y, m, ids in page.date_groups
],
}
)
@gallery_bp.route("/similar", methods=["GET"])
async def similar():
"""Visual "more like this": images ranked by cosine distance to the
`similar_to` image's embedding. Composes with the scope filters (AND) but
ignores post_id and sort. Bounded top-N, no cursor."""
try:
similar_to = int(request.args["similar_to"])
limit = int(request.args.get("limit", "100"))
filters, _sort = _parse_filters()
except (KeyError, ValueError):
return jsonify({"error": "similar_to query param required"}), 400
# Explore passes exclude_wip=1 to also drop work-in-progress from the
# rabbit-hole; the gallery's own "similar" button omits it (keeps wip, #1274).
exclude_wip = request.args.get("exclude_wip") in ("1", "true", "True")
# post_id is the exclusive post-detail view — not a similarity scope.
# include_hidden is a gallery-browse flag; similar() has its OWN presentation
# exclusion (a similarity-quality concern, #1274), so drop it here (#141).
scope = {
k: v for k, v in filters.items() if k not in ("post_id", "include_hidden")
}
async with get_session() as session:
svc = GalleryService(session)
try:
images = await svc.similar(
image_id=similar_to, limit=limit, exclude_wip=exclude_wip, **scope)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
if images is None:
return jsonify({"error": "not found"}), 404
return jsonify(
{
"images": [_image_json(i) for i in images],
"next_cursor": None,
"date_groups": [],
}
)
@gallery_bp.route("/timeline", methods=["GET"])
async def timeline():
try:
filters, _sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
buckets = await svc.timeline(**filters)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
[{"year": b.year, "month": b.month, "count": b.count} for b in buckets]
)
@gallery_bp.route("/facets", methods=["GET"])
async def facets():
try:
filters, _sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
f = await svc.facets(**filters)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
{
"total": f.total,
"platforms": f.platforms,
"untagged": f.untagged,
"no_artist": f.no_artist,
"date_min": f.date_min.isoformat() if f.date_min else None,
"date_max": f.date_max.isoformat() if f.date_max else None,
}
)
@gallery_bp.route("/jump", methods=["GET"])
async def jump():
try:
year = int(request.args["year"])
month = int(request.args["month"])
filters, sort = _parse_filters()
except (KeyError, ValueError):
return jsonify({"error": "year and month query params required"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
cursor = await svc.jump_cursor(
year=year, month=month, sort=sort, **filters,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify({"cursor": cursor})
# -- Hidden-view review (#141): auto-hidden chrome flagged "also looks like
# content", surfaced in the gallery's Show-hidden review strip. -----------
@gallery_bp.route("/hidden-review", methods=["GET"])
async def hidden_review():
"""Unresolved system-tag auto-apply review flags (chrome + process, #1464),
most-concerning first (highest content score) — for the review strip. `mode`
tells the client whether the flagged tag hid the image ('chrome') or left it
visible ('process'), which decides the resolve labels (un-hide vs remove-tag)."""
ptag = aliased(Tag)
ctag = aliased(Tag)
async with get_session() as session:
rows = (await session.execute(
select(
PresentationReview.image_record_id,
PresentationReview.tag_id,
PresentationReview.conflict_tag_id,
PresentationReview.conflict_score,
PresentationReview.mode,
ImageRecord.path, ImageRecord.thumbnail_path,
ImageRecord.sha256, ImageRecord.mime,
ptag.name.label("tag_name"),
ctag.name.label("conflict_name"),
)
.join(ImageRecord, ImageRecord.id == PresentationReview.image_record_id)
.join(ptag, ptag.id == PresentationReview.tag_id)
.outerjoin(ctag, ctag.id == PresentationReview.conflict_tag_id)
.where(PresentationReview.resolved_at.is_(None))
.order_by(PresentationReview.conflict_score.desc())
)).all()
return jsonify({"items": [
{
"image_id": r.image_record_id,
"tag_id": r.tag_id,
"tag_name": r.tag_name,
"conflict_tag_id": r.conflict_tag_id,
"conflict_name": r.conflict_name,
"conflict_score": r.conflict_score,
"mode": r.mode,
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
"image_url": image_url(r.path),
}
for r in rows
]})
@gallery_bp.route(
"/hidden-review/<int:image_id>/<int:tag_id>/keep", methods=["POST"]
)
async def hidden_review_keep(image_id, tag_id):
"""Keep the auto-hide: resolve the flag; the tag stays applied (#141)."""
async with get_session() as session:
await session.execute(
update(PresentationReview)
.where(
PresentationReview.image_record_id == image_id,
PresentationReview.tag_id == tag_id,
)
.values(resolved_at=datetime.now(UTC))
)
await session.commit()
return "", 204
@gallery_bp.route(
"/hidden-review/<int:image_id>/<int:tag_id>/unhide", methods=["POST"]
)
async def hidden_review_unhide(image_id, tag_id):
"""Un-hide: remove the presentation tag (image returns to the gallery), record
a rejection so the head LEARNS it misfired, and resolve the flag (#141)."""
from sqlalchemy.dialects.postgresql import insert as pg_insert
async with get_session() as session:
await session.execute(
delete(image_tag).where(
image_tag.c.image_record_id == image_id,
image_tag.c.tag_id == tag_id,
)
)
await session.execute(
pg_insert(TagSuggestionRejection)
.values(image_record_id=image_id, tag_id=tag_id)
.on_conflict_do_nothing()
)
await session.execute(
update(PresentationReview)
.where(
PresentationReview.image_record_id == image_id,
PresentationReview.tag_id == tag_id,
)
.values(resolved_at=datetime.now(UTC))
)
await session.commit()
return "", 204
@gallery_bp.route("/image/<int:image_id>", methods=["GET"])
async def image_detail(image_id: int):
async with get_session() as session:
svc = GalleryService(session)
payload = await svc.get_image_with_tags(image_id)
if payload is None:
return jsonify({"error": "not found"}), 404
return jsonify(payload)